Michael Slawson

Built and sold a 7-figure agency, GTM @ Clipboard Health, Hum Capital, Deloitte

How to build a Github repo for your revops and GTM system

Ben Holley

10+ GTM systems in production, GTM @ Apero, AirOps, Cyft, Clay, Lightyear

Map the customer, team, process, and business context an agent needs, and leave out the noise that confuses it.

What belongs in your repo, and what doesn't

Organize by your GTM motion instead of by vendor/model, and route every change through review so nothing drifts

Structure your repo so it outlasts your tools

Give agents memory, current state, and rules they can't ignore, so the repo gets better every time they use it.

Set up your repo so agents work the way you want

Build AI Agent Skills that Actually Work - 3 Hours Hands-on Workshop

Product Leader and Super IC at Google

Google

Disney+ Hotstar

Zynga

Anshumani Ruddra

Product Super IC at Google with 22+ years crafting experiences and blockbuster products

Cohort 06

Cohort 07

Most product builders use AI agents the same way they used search - typing queries and hoping for the best. That's leaving most of the value on the table.The teams pulling ahead aren't using better prompts. They're teaching their agents. Agent Skills are reusable, testable instruction sets that tell AI agents exactly how to handle specific workflows: your deployment process, your code review standards, your team's edge cases. Write one skill well, and every agent on your team benefits from it, every time, automatically.The problem: nobody is teaching product builders how to create them. Most documentation is written for a narrow technical audience, and the tooling is fragmented across Claude Code, Codex, and Gemini.In this hands-on workshop, you'll go from zero to a working skill installed in your own agent: one that reflects your real workflows, not generic templates. You'll also learn how to evaluate and improve skills systematically, so they get better over time instead of drifting.If you build or are hoping to build products with AI agents: this is the highest-leverage skill you can develop right now.

🤖 Learn to build procedural Agent Skills, transforming your professional mindset from solo prompter to manager of elite AI agents

Shift to an AI Management Mindset

Build Custom, Reusable Agent Skills

Leverage the Open-Source Ecosystem

Evaluate and Iterate for 10x Output

Product Managers: who use Claude Code or Codex daily but rely on ad-hoc prompts - and want repeatable, team-shareable AI workflows.

Entrepreneurs &amp; Founders: building AI-native products who need their agents to encode business logic, not just generate code on demand.

Tech Executives &amp; Product Leaders: who want their teams to stop reinventing prompts and start shipping a shared skills library.

Build a team of Agents from Zero. 
No coding experience needed. 

3x VP Marketing 

Laura Beaulieu

3x VP Marketing, 2025 CMO of the Year finalist, | Founder GrowthLoops.io

Cohort 2

Cohort 3

<blockquote>Fewer than 1% of people know how to build with AI right now. In three weeks, you'll be one of them. More importantly, you'll feel like one of them.Here's my goal for you, and I mean every single student: you walk out confident navigating, building, and shipping in Claude Code. <ul><li>Confident opening Claude Code instead of avoiding it</li><li>Confident building your own skills from scratch</li><li>Confident connecting Claude to your tools</li></ul>Get the foundation right and everything you build after it gets easier. That is the whole point of these three weeks.That confidence is the entire point. We build together, live. And you have resources between sessions: weekly office hours, step-by-step worksheets you keep, and full recordings. Nobody gets left at "I think I get it."This is for you if you're: <ul><li>A marketer who's ready to 10x what you can do. </li><li>A lean team that needs more output without more headcount. </li><li>Or a founder wearing every hat who'd rather build the systems than buy ten more tools to duct-tape together.</li></ul>You'll start from zero. You won't leave there.</blockquote>

Start from Zero. Build Marketing Agents. No developer experience required. 

Build a Brand Brain that makes every agent sound like you

Connect your real tools so Claude can act, not just chat

Deploy an agent that spies on your competitors for you

Generate C-suite-ready reports an agency would bill you for

Build a full lead-gen funnel that replaces your agency

Walk away a builder who can solve your own problems

This course runs entirely in Claude Code. You'll need an active subscription. We'll cover everything else

A paid Claude account (Pro or Max)

We use VS Code as our workspace. It's free. You'll download it as part of the setup guide sent before Day 1.

No coding experience required

You build alongside other marketers and get direct feedback from Laura in real time. This is hands-on, not a lecture

Live cohort format

Marketers who need to 10x themselves and ready to build their own agents from scratch.

Founders who are the entire marketing team and need to produce like a team of 10 without hiring one.

Leaders who want to see what's possible and want the hands-on agent building skills that no other course is teaching yet.

A team of agents you run, no code, for product and growth.

VP, Growth | Ex-Microsoft | 

Microsoft

Canon EMEA

Pfizer

Grace Man

Agentic Growth Marketing | Ex-Microsoft 

Build Growth Agents in Claude Code 

<blockquote>You own the signals and the roadmap, but growth and go-to-market still run as three separate scrambles. Product, growth, and marketing keep their own tools, and the real work lands back on you.The rare thing is running them as one system: the intersection of product, growth, and marketing. Product owns the signals and the roadmap, growth owns pipeline, marketing owns demand.This workshop is built to bridge that gap.Most growth leaders and operators already use AI. Very few have built a system with it. That gap is your edge, and it is still open.The old way is one task, one prompt, one tool. Your product and pipeline fire signals all day: pricing-page visits, activation stalls, usage decay, hot replies. The new way is a team of agents that act on them and compound at ten times the quality.There is no shortage of information about Claude Code online. The difference is learning by doing, live on your own account, no code.You will leave with:<ul><li>Confidence using Claude Code, no code needed</li><li>Agents that talk to each other and act on real buying and product signals</li><li>Compound growth at 10x output quality</li></ul>The teams that build this now will outpace the ones still buying tools.</blockquote>

Build the five agents that run product, growth, and marketing as one system in Claude: signal, content, outbound, retention, and the gate.

 Set up the shared context layer and design system in Claude

Build the signal watcher that reads your real product data

Build the research and content agent that drafts in your voice

Build a warm outbound sequence with exit logic built in

Build the retention agent pointed at usage decay

Set the gate tiers and cost caps that keep it all safe

Claude Pro or Max with Claude Code installed, no API key. Connectors on where you use them: Gmail, Notion, Slack, CRM/Hubspot, GitHub.

A paid Claude account and Claude Code, no coding 

A brand guideline or a site to pull one from, real transcripts from Granola or Fireflies, and a lead list or a CRM connected to Claude.

Your own brand, content, and pipeline material

A product signal source your agents can read, analytics, usage, or CRM, plus one real growth problem you want them to work on.

Real product data and one problem to solve

Product and growth-led PMs who own the signals, usage, and roadmap, and want agents that act on that product data, not more dashboards.

Growth and marketing leaders who own pipeline and demand, and want content, outbound, and retention running on real signals, not guesswork.

Builders, operators, and founders doing all three, the team of one, who want to build the agent system on their own data, not just use AI.

You stop arguing about whether the agent is good, and start showing the number, the rubric behind it, and the decision it justifies.

Author, AI Agent Evaluation (Springer)

Abdullah Mansoor

Co-author of AI Agent Evaluation (Springer 2026), written for non-coders.

Cohort 1

You shipped an AI agent. It demos beautifully. Then a board member, a customer, or your own gut asks the question you have been avoiding: how do you know it works? Most teams answer with more testing, more prompt tuning, and a dashboard nobody trusts. The gap does not close, because the missing piece is not effort. It is a system: a written standard for what good means, an instrument that measures against it, and a loop that runs on a schedule. This is the companion course to AI Agent Evaluation (Mansoor and Bokhari, Springer 2026), cut for the person who makes the release decision rather than writes the code. Six modules take you from naming the failure you are afraid of, to writing a contract your agent has to honor, to scoring it on four dimensions, to running a loop that improves it every week. Every tool, framework and metric is introduced at concept level. After a module you can hold your own with your engineers using these terms. No lesson asks you to open a terminal. You leave with seven artifacts built on your own agent: a contract, a rubric with anchors, a benchmark set, a failure taxonomy, a release gate, a cost and latency budget, and a seven-step playbook.

A demo proves it worked once. Production asks you to prove it works every time.

Name the failure pattern your agent is most likely to hit

Write a one-page agent contract

Score your agent on the four dimensions that decide readiness

Build a rubric two independent raters would score the same way

Run the Biruni Loop so quality improves on a schedule

Put cost and latency on the same row as quality

Every exercise is built on your own agent, so you leave with a contract and a rubric for something real rather than a worked example.

An AI agent in production, or one you are about to ship

Everything is taught at concept level. You will hold your own with your engineers using these terms without opening a terminal.

No coding required, and no prior testing or evaluation background

The templates only pay off against a decision you actually have to make, so bring a release you are genuinely unsure about.

Willingness to bring one real agent and one real release decision

Founders whose agent demos beautifully, then answers the same question two ways on a Tuesday. You need the rate, not the anecdote.

Product leads who own the AI feature but not the code. Engineers report a score. You cannot tell if the product improved or the test eased.

Technical founders who stopped coding. You read a system diagram fine. You want the vocabulary back at concept level, without a code tour.

Agentic AI

Coding with AI

AI Workflows

Claude Code

OpenClaw

Vibe Coding

AI Evals

AI Transformation

RAG & Search

AI for PMs

AI for Engineers

AI for Designers

AI for Marketers

AI for Founders

Product Sense

Product Discovery

User Research

Prototyping

Growth

Analytics

Tech Foundations

Strategy

Influence

Leadership

Career Growth

Machine Learning

LLM Ops

Context Eng

Security

System Design

Figma

Design Systems

Visual Design

Design Strategy

Automation

Content Marketing

Demand Gen

Go-to-Market

Product Marketing

Positioning

Social Media

Brand

B2B Marketing

SEO & AEO

AI for Leaders

AI Governance

Communication

Management

People Operations

Exec Presence

Storytelling

Goal-setting

Personal Brand

Fundraising

Everyone

Operators

Data Scientists

Business Analysts

User Researchers

Customer Success

Project Managers

HR Professionals

Sales People

Lawyers

Finance

Investors

Real Estate

Educators

Creators

Operations professionals who optimize processes and manage day-to-day business functions.

Marketers who drive brand awareness, customer acquisition, and growth across channels.

Applying AI tools and techniques to professional workflows — assign alongside more specific AI topics.

Building autonomous AI agent systems that take actions, use tools, and orchestrate multi-step workflows.

Planning and executing product launches, market entry strategies, and cross-functional go-to-market coordination.

Automating professional workflows with AI tools — productivity, operations, and task automation.

Designing and optimizing the context window for LLM applications — prompt structure, memory, and information retrieval.

How to build a Github repo for your revops and GTM system

What you'll learn

Why this topic matters

You'll learn from

Michael Slawson

Ben Holley